Hybrid Analytical Modeling of Pending Cache Hits, Data Prefetching,
XI E. CHEN
TOR M. AAMODT
University of British Columbia
This paper proposes techniques to predict the performance impact of pending cache hits, hardware prefetch-
ing, and miss status holding register resources on superscalar microprocessors using hybrid analytical models.
The proposed models focus on timeliness of pending hits and prefetches and account for a limited number
of MSHRs. They improve modeling accuracy of pending hits by 3.9x and when modeling data prefetching, a
limited number of MSHRs, or both, these techniques result in average errors of 9.5% to 17.8%. The impact
of non-uniform DRAM memory latency is shown to be approximated well by using a moving average of
memory access latency.
Categories and Subject Descriptors: C.4 [Computer Systems Organization]: Performance of Systems--
General Terms: Performance
Additional Key Words and Phrases: Analytical modeling, pending hit, data prefetching, miss status holding